Example-Based Super-Resolution Land Cover Mapping Using Support Vector Regression

Zhang, Yihang; Du, Yingxun; Ling, Feng; Fang, Shiming; Li, Xiaodong

doi:10.1109/jstars.2014.2305652

Cited by 54 publications

(58 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decades, many SRM methods have been proposed. These methods involve the pixel swapping algorithm [7,13], Hopfield neural networks [14][15][16], subpixel/pixel spatial attraction models [17][18][19], Markov random fields [20][21][22][23], the geometric methods [24,25], geostatistical methods [26][27][28], artificial intelligence-based algorithms [29][30][31][32][33] and interpolation-based methods [34][35][36]. These methods have obtained acceptable performances in various applications, such as urban tree identification [37], urban building extraction [38], floodplain inundation mapping [39,40] and land use mapping [41].…”

mentioning

confidence: 99%

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Chen

Heuvelink

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

mentioning

confidence: 99%

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Chen

Heuvelink

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

“…In this paper, a sub-image, rather than the entire hyperspectral image, is fed to the 3D-FCNN. Specifically, as shown in Table 1, the input is restricted as a 33 33 1 c × × × -pixel sub-image cube, where 33 33 × is spatial dimensions, c is the special dimension depending on the sensor properties, and the color channel is set as 1 for HSIs. Therefore, all the filers in the successive convolution layers are designed to learn spectral information from c contiguous spectral bands.…”

Section: The Architecture Of the Proposed 3d-fcnnmentioning

confidence: 99%

“…Recently, sub-pixel mapping (SPM) techniques, which predict the location of land cover classes within a coarse pixel (mixed pixel) [19,20], have also been proposed to generate a high-resolution classification map using fractional abundance images. Various methods based on linear optimization technique [21], pixel/sub-pixel spatial attraction model [22], pixel swapping algorithm [23], maximum a posteriori (MAP) model [24,25], Markov random field (MRF) [26,27], artificial neural network (ANN) [28][29][30], simulated annealing [31], total variant model [32], support vector regression [33], and collaborative representation [34] are proposed. In general, sub-pixel based analysis only overcomes the limitation in spatial-resolution for certain applications, e.g., classification and target detection.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network

et al. 2017

View full text Add to dashboard Cite

Hyperspectral images are well-known for their fine spectral resolution to discriminate different materials. However, their spatial resolution is relatively low due to the trade-off in imaging sensor technologies, resulting in limitations in their applications. Inspired by recent achievements in convolutional neural network (CNN) based super-resolution (SR) for natural images, a novel three-dimensional full CNN (3D-FCNN) is constructed for spatial SR of hyperspectral images in this paper. Specifically, 3D convolution is used to exploit both the spatial context of neighboring pixels and spectral correlation of neighboring bands, such that spectral distortion when directly applying traditional CNN based SR algorithms to hyperspectral images in band-wise manners is alleviated. Furthermore, a sensor-specific mode is designed for the proposed 3D-FCNN such that none of the samples from the target scene are required for training. Fine-tuning by a small number of training samples from the target scene can further improve the performance of such a sensor-specific method. Extensive experimental results on four benchmark datasets from two well-known hyperspectral sensors, namely hyperspectral digital imagery collection experiment (HYDICE) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed 3D-FCNN outperforms several existing SR methods by ensuring higher quality both in reconstruction and spectral fidelity.

show abstract

“…For the spatial model term, the spatial dependence model that aims to make the fine spatial resolution land cover map have the maximal spatial dependence is widely used [19,22,34,56]. The spatial model can also be constructed through the incorporation of information provided by additional dataset [57,58], or learned from the training image [59][60][61]. A comprehensive review of these models is beyond the scope of this paper, and more information can be found in relative literatures.…”

Section: Sub-pixel Mappingmentioning

confidence: 99%

Assessing a Temporal Change Strategy for Sub-Pixel Land Cover Change Mapping from Multi-Scale Remote Sensing Imagery

Ling

Foody

et al. 2016

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Abstract:Remotely sensed imagery is an attractive source of information for mapping and monitoring land cover. Fine spatial resolution imagery is typically acquired infrequently, but fine temporal resolution systems commonly provide coarse spatial resolution imagery. Sub-pixel land cover change mapping is a method that aims to use the advantages of these multiple spatial and temporal resolution sensing systems. This method produces fine spatial and temporal resolution land cover maps, by updating fine spatial resolution land cover maps using coarse spatial resolution remote sensing imagery. A critical issue for sub-pixel land cover change mapping is downscaling coarse spatial resolution fraction maps estimated by soft classification to a fine spatial resolution land cover map. The relationship between a historic fine spatial resolution map and a contemporary fine spatial resolution map to be estimated at a more recent date plays an important role in the downscaling procedure. A change strategy based on the assumption that the change for each land cover class in a coarse spatial resolution pixel is unidirectional was shown to be a promising means to describe this relationship. This paper aims to assess this change strategy by analyzing the factors that affect the accuracy of the change strategy, using six subsets of the National Land Cover Database (NLCD) of USA. The results show that the spatial resolution of coarse pixels, the time interval of the previous fine resolution land cover map and the current coarse spatial resolution images, and the thematic resolution of the used land cover class scheme have considerable influence on the accuracy of the change strategy. The accuracy of the change strategy decreases with the coarsening of spatial resolution, an increase of time interval, and an increase of thematic resolution. The results also indicate that, when the historic land cover map has a 30 m resolution, like the NLCD, the average accuracy of the change strategy is still as high as 92% when the coarse spatial resolution data used had a resolution of~1000 m, confirming the effectiveness of the change strategy used in sub-pixel land cover change mapping for use with popular remote sensing systems.

show abstract

Example-Based Super-Resolution Land Cover Mapping Using Support Vector Regression

Cited by 54 publications

References 47 publications

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Object-Based Superresolution Land-Cover Mapping From Remotely Sensed Imagery

Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network

Assessing a Temporal Change Strategy for Sub-Pixel Land Cover Change Mapping from Multi-Scale Remote Sensing Imagery

Contact Info

Product

Resources

About